Re: [PATCH 6/6] hw/cxl: Add clear poison mailbox command support.

[Ira Weiny]

Jonathan Cameron wrote:
> Current implementation is very simple so many of the corner
> cases do not exist (e.g. fragmenting larger poison list entries)
> 
> Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> ---
>  hw/cxl/cxl-mailbox-utils.c  | 77 +++++++++++++++++++++++++++++++++++++
>  hw/mem/cxl_type3.c          | 36 +++++++++++++++++
>  include/hw/cxl/cxl_device.h |  1 +
>  3 files changed, 114 insertions(+)
> 
> diff --git a/hw/cxl/cxl-mailbox-utils.c b/hw/cxl/cxl-mailbox-utils.c
> index 7d3f7bcd3a..f56c76b205 100644
> --- a/hw/cxl/cxl-mailbox-utils.c
> +++ b/hw/cxl/cxl-mailbox-utils.c
> @@ -65,6 +65,7 @@ enum {
>      MEDIA_AND_POISON = 0x43,
>          #define GET_POISON_LIST        0x0
>          #define INJECT_POISON          0x1
> +        #define CLEAR_POISON           0x2
>  };
>  
>  struct cxl_cmd;
> @@ -474,6 +475,80 @@ static CXLRetCode cmd_media_inject_poison(struct cxl_cmd 
> *cmd,
>      return CXL_MBOX_SUCCESS;
>  }
>  
> +static CXLRetCode cmd_media_clear_poison(struct cxl_cmd *cmd,
> +                                         CXLDeviceState *cxl_dstate,
> +                                         uint16_t *len)
> +{
> +    CXLType3Dev *ct3d = container_of(cxl_dstate, CXLType3Dev, cxl_dstate);
> +    CXLPoisonList *poison_list = &ct3d->poison_list;
> +    CXLType3Class *cvc = CXL_TYPE3_GET_CLASS(ct3d);
> +    struct clear_poison_pl {
> +        uint64_t dpa;
> +        uint8_t data[64];
> +    };
> +    CXLPoison *ent;
> +
> +    struct clear_poison_pl *in = (void *)cmd->payload;
> +
> +    if (in->dpa + 64 > cxl_dstate->mem_size) {
> +        return CXL_MBOX_INVALID_PA;
> +    }
> +
> +    QLIST_FOREACH(ent, poison_list, node) {
> +        /*
> +         * Test for contained in entry. Simpler than general case
> +         * as clearing 64 bytes and entries 64 byte aligned
> +         */
> +        if ((in->dpa < ent->start) || (in->dpa >= ent->start + ent->length)) 
> {
> +            continue;
> +        }
> +        /* Do accounting early as we know one will go away */
> +        ct3d->poison_list_cnt--;
> +        if (in->dpa > ent->start) {
> +            CXLPoison *frag;
> +            if (ct3d->poison_list_cnt == CXL_POISON_LIST_LIMIT) {

Isn't this always impossible because poison_list_cnt was just decremented?

I wonder if the early accounting is correct with this check.

> +                cxl_set_poison_list_overflowed(ct3d);
> +                break;
> +            }
> +            frag = g_new0(CXLPoison, 1);
> +
> +            frag->start = ent->start;
> +            frag->length = in->dpa - ent->start;
> +            frag->type = ent->type;
> +
> +            QLIST_INSERT_HEAD(poison_list, frag, node);
> +            ct3d->poison_list_cnt++;
> +        }
> +        if (in->dpa + 64 < ent->start + ent->length) {
> +            CXLPoison *frag;
> +
> +            if (ct3d->poison_list_cnt == CXL_POISON_LIST_LIMIT) {
> +                cxl_set_poison_list_overflowed(ct3d);
> +                break;
> +            }
> +
> +            frag = g_new0(CXLPoison, 1);
> +
> +            frag->start = in->dpa + 64;
> +            frag->length = ent->start + ent->length - frag->start;
> +            frag->type = ent->type;
> +            QLIST_INSERT_HEAD(poison_list, frag, node);
> +            ct3d->poison_list_cnt++;
> +        }
> +        /* Any fragments have been added, free original entry */
> +        QLIST_REMOVE(ent, node);

Seems safer to decrement here and check limit prior to adding the
fragments above.

> +        g_free(ent);
> +        break;
> +    }
> +    /* Clearing a region with no poison is not an error so always do so */
> +    if (cvc->set_cacheline)

Per Qemu coding you need '{'.  But is this check needed? ...

> +        if (!cvc->set_cacheline(ct3d, in->dpa, in->data)) {
> +            return CXL_MBOX_INTERNAL_ERROR;
> +        }
> +
> +    return CXL_MBOX_SUCCESS;
> +}
> +
>  #define IMMEDIATE_CONFIG_CHANGE (1 << 1)
>  #define IMMEDIATE_DATA_CHANGE (1 << 2)
>  #define IMMEDIATE_POLICY_CHANGE (1 << 3)
> @@ -505,6 +580,8 @@ static struct cxl_cmd cxl_cmd_set[256][256] = {
>          cmd_media_get_poison_list, 16, 0 },
>      [MEDIA_AND_POISON][INJECT_POISON] = { "MEDIA_AND_POISON_INJECT_POISON",
>          cmd_media_inject_poison, 8, 0 },
> +    [MEDIA_AND_POISON][CLEAR_POISON] = { "MEDIA_AND_POISON_CLEAR_POISON",
> +        cmd_media_clear_poison, 72, 0 },
>  };
>  
>  void cxl_process_mailbox(CXLDeviceState *cxl_dstate)
> diff --git a/hw/mem/cxl_type3.c b/hw/mem/cxl_type3.c
> index 3585f78b4e..8adc725edc 100644
> --- a/hw/mem/cxl_type3.c
> +++ b/hw/mem/cxl_type3.c
> @@ -925,6 +925,41 @@ static void set_lsa(CXLType3Dev *ct3d, const void *buf, 
> uint64_t size,
>       */
>  }
>  
> +static bool set_cacheline(CXLType3Dev *ct3d, uint64_t dpa_offset, uint8_t 
> *data)
> +{
> +    MemoryRegion *vmr = NULL, *pmr = NULL;
> +    AddressSpace *as;
> +
> +    if (ct3d->hostvmem) {
> +        vmr = host_memory_backend_get_memory(ct3d->hostvmem);
> +    }
> +    if (ct3d->hostpmem) {
> +        pmr = host_memory_backend_get_memory(ct3d->hostpmem);
> +    }
> +
> +    if (!vmr && !pmr) {
> +        return false;
> +    }
> +
> +    if (dpa_offset + 64 > int128_get64(ct3d->cxl_dstate.mem_size)) {
> +        return false;
> +    }
> +
> +    if (vmr) {
> +        if (dpa_offset <= int128_get64(vmr->size)) {
> +            as = &ct3d->hostvmem_as;
> +        } else {
> +            as = &ct3d->hostpmem_as;
> +            dpa_offset -= vmr->size;
> +        }
> +    } else {
> +        as = &ct3d->hostpmem_as;
> +    }
> +
> +    address_space_write(as, dpa_offset, MEMTXATTRS_UNSPECIFIED, &data, 64);
> +    return true;
> +}
> +
>  void cxl_set_poison_list_overflowed(CXLType3Dev *ct3d)
>  {
>          ct3d->poison_list_overflowed = true;
> @@ -1146,6 +1181,7 @@ static void ct3_class_init(ObjectClass *oc, void *data)
>      cvc->get_lsa_size = get_lsa_size;
>      cvc->get_lsa = get_lsa;
>      cvc->set_lsa = set_lsa;
> +    cvc->set_cacheline = set_cacheline;

...  This is always set?

Ira

>  }
>  
>  static const TypeInfo ct3d_info = {
> diff --git a/include/hw/cxl/cxl_device.h b/include/hw/cxl/cxl_device.h
> index 3cb77fe8a5..0a05f21e40 100644
> --- a/include/hw/cxl/cxl_device.h
> +++ b/include/hw/cxl/cxl_device.h
> @@ -326,6 +326,7 @@ struct CXLType3Class {
>                          uint64_t offset);
>      void (*set_lsa)(CXLType3Dev *ct3d, const void *buf, uint64_t size,
>                      uint64_t offset);
> +    bool (*set_cacheline)(CXLType3Dev *ct3d, uint64_t dpa_offset, uint8_t 
> *data);
>  };
>  
>  MemTxResult cxl_type3_read(PCIDevice *d, hwaddr host_addr, uint64_t *data,
> -- 
> 2.37.2
>